data_utils.py 文件源码

def urlretrieve(url, filename, reporthook=None, data=None):
        """Replacement for `urlretrive` for Python 2.

        Under Python 2, `urlretrieve` relies on `FancyURLopener` from legacy
        `urllib` module, known to have issues with proxy management.

        # Arguments
            url: url to retrieve.
            filename: where to store the retrieved data locally.
            reporthook: a hook function that will be called once
                on establishment of the network connection and once
                after each block read thereafter.
                The hook will be passed three arguments;
                a count of blocks transferred so far,
                a block size in bytes, and the total size of the file.
            data: `data` argument passed to `urlopen`.
        """
        def chunk_read(response, chunk_size=8192, reporthook=None):
            total_size = response.info().get('Content-Length').strip()
            total_size = int(total_size)
            count = 0
            while 1:
                chunk = response.read(chunk_size)
                count += 1
                if not chunk:
                    reporthook(count, total_size, total_size)
                    break
                if reporthook:
                    reporthook(count, chunk_size, total_size)
                yield chunk

        response = urlopen(url, data)
        with open(filename, 'wb') as fd:
            for chunk in chunk_read(response, reporthook=reporthook):
                fd.write(chunk)